Non-asymptotic Error Bounds For Constant Stepsize Stochastic Approximation For Tracking Mobile Agents
arXiv:1802.07759 · doi:10.1007/s00498-019-00249-4
Abstract
This work revisits the constant stepsize stochastic approximation algorithm for tracking a slowly moving target and obtains a bound for the tracking error that is valid for the entire time axis, using the Alekseev non-linear variation of constants formula. It is the first non-asymptptic bound for the entire time axis in the sense that it is not based on the vanishing stepsize limit and associated limit theorems unlike prior works, and captures clearly the dependence on problem parameters and the dimension.
arXiv commentExpanded and revised
References in corpus (3)
- Non-strongly-convex smooth stochastic approximation with convergence rate O(1/n)
- Stability Analysis of Nonlinear Time-Varying Systems by Lyapunov Functions with Indefinite Derivatives
- Exponential inequalities for martingales and asymptotic properties of the free energy of directed polymers in random environment